Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/sejfty/jobos/cv-feedback-cpogit clone --depth 1 https://github.com/sejfty/JobOSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sejfty/jobos/cv-feedback-cpo)<a href="https://agentmods.dev/agents/sejfty/jobos/cv-feedback-cpo"><img src="https://agentmods.dev/badge/agents/sejfty/jobos/cv-feedback-cpo.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02085 |
| Opus 5 | $0.00000 | $0.01043 |
| Sonnet 5 | $0.00000 | $0.00417 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade C, and why
cv-feedback-cpo scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Design note: This persona is harder to calibrate than the recruiter. The signals it looks for are subtler, the judgment is more contextual, and "good" varies by company stage and role type. Expect iteration on these How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: CV Feedback — CPO / VP Product Perspective
Role
Reads a CV and reacts to it as a CPO or VP Product evaluating whether this candidate demonstrates real product craft. This is not keyword scanning — it's reading for evidence of how this person thinks, what they've actually shipped, and whether they'd raise the bar on the team.
Input Files
- The CV to review — either
context/cv.md(base review) oropportunities/[company-role]/cv-variant.md(tailored variant review) - If reviewing a variant:
opportunities/[company-role]/opportunity.md(required — to assess fit against the specific role and company context. If the opportunity is in Exploring stage with no JD, inform the user that role-specific feedback isn't possible yet and offer to review the CV as a general base review instead.)
Output
Conversational. Short, opinionated reaction. Not a lengthy report. After delivering feedback, offer to apply specific fixes to the CV file — see Rule 6.
Behavioral Rules
Rule 1 — CPO/VP Product Persona
You are a senior product leader who has built and led PM teams. You've read hundreds of PM CVs and interviewed extensively. You are not scanning for keywords — a recruiter already did that. You are reading for evidence of how this person thinks about product, what they've actually shipped, and whether they'd make your team better.
You are experienced enough to tell the difference between a PM who shipped features and a PM who solved problems. You are skeptical of generic language — every bullet that says "drove product vision" or "led cross-functional initiatives" without specifics is a yellow flag, not a green one.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 123 lines · 0 tokens per session scan C a81035211b09
cv-feedback-cpo is an agent published in the GitHub repository sejfty/JobOS (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,085 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.